Normalized claim
Time: 10 minutes decrease
Policy document processing time dropped from 10 minutes to under 60 seconds.
OneAssure: Document AI and Gemini Enterprise Agent Platform automate health insurance policy document extraction
Use case typeCustomer service automationUpdated Jun 13, 2026
OneAssure is a Bengaluru-based insurtech that simplifies the health insurance journey in India through a digital-first, human-centric model. Its operations team had been manually extracting data from complex PDF policy documents, typing up to 30 fields per file and spending about 10 minutes on each document, which created errors and payout disputes across a network of more than 250 advisors and partners. By moving to Google Cloud, OneAssure implemented an AI-based extraction and advisory workflow to improve document processing, advisor support, and customer guidance.
Reported outcomes
+90%
quantified impactCustomer experience
10 minutestime60 secondstime95-98%accuracy30%quantified impact+20%quantified impact
Strategic outcomes
Speed & agilityAutomated policy document extraction workflowNew product / capabilityLaunched real-time policy assessment chatbotCustomer experience & trustImproved advisor and partner supportScale & capacitySupported growing user and advisor volumes
Catalog median for customer experience deployments: +25% across 53 reported metrics. Compare benchmarks →
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Time: 60 seconds decrease
Policy document processing time dropped from 10 minutes to under 60 seconds.
Normalized claim
Accuracy: 95-98% increase
Data extraction accuracy improved from 95% to 98%.
Normalized claim
Quantified impact: 30%
Manual query volume between internal teams and partners fell by 30%.
Normalized claim
Quantified impact: 90% increase
The company reported maintaining a 90% advisor retention rate and a 20% increase in active users attributed to the AI-driven advisory tools.
Normalized claim
Quantified impact: 20% increase
The company reported maintaining a 90% advisor retention rate and a 20% increase in active users attributed to the AI-driven advisory tools.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- OneAssure
- Provider
- GCP
- Maturity
- Production
- Linked source
- Google Cloud Customer Story
It used Gemini Enterprise Agent Platform to tune and orchestrate AI model selection for extraction tasks, and also deployed a Gemini-powered D2C chatbot for real-time policy assessments and coverage gap analysis
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 4
- 1Document processing automation
- 2Customer service automation
- 3Advisor support automation
- Manual extraction from mixed-image and text PDFs was slow and error-prone.
- Processing mistakes such as miscalculated premiums or missed nominees could lead to payout inaccuracies and disputes.
- The team needed a more scalable workflow to support growing monthly user volumes and a large advisor network.
- OneAssure moved its infrastructure to Google Kubernetes Engine and used Document AI to automate policy document extraction.
- The company built the extraction tool in about one week, replacing manual data entry with an automated workflow.
- It used Gemini Enterprise Agent Platform to tune and orchestrate AI model selection for extraction tasks, and also deployed a Gemini-powered D2C chatbot for real-time policy assessments and coverage gap analysis.
- The GEAP-based agentic workflow also powers advisor and partner question answering to reduce back-and-forth manual queries.
- Policy document processing time dropped from 10 minutes to under 60 seconds.
- Data extraction accuracy improved from 95% to 98%.
- Manual query volume between internal teams and partners fell by 30%.
- The chatbot generated 150-200 high-quality monthly leads.
- The company reported maintaining a 90% advisor retention rate and a 20% increase in active users attributed to the AI-driven advisory tools.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: May 15, 2026Publisher: Google Cloud Customer StoryEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.